Designing exceptional gas-separation polymer membranes using machine learning
Designing exceptional gas-separation polymer membranes using machine learning
复制标题
DOI：
10.1126/sciadv.aaz4301
复制
发表时间：
2020-05-01
期刊：
影响因子：
13.6
通讯作者：
Kumar, Sanat K.
中科院分区：
文献类型：
--
作者：
Barnett, J. Wesley;Bilchak, Connor R.;Kumar, Sanat K.
聚合物膜设计领域主要基于经验观察，这限制了用于分离给定气体对的优化的新材料的发现。我们没有依赖于详尽的实验研究，而是使用聚合物重复单元的拓扑，基于路径的哈希来训练机器学习（ML）算法。我们使用了一组有限的实验气体渗透性数据，用于六种不同的气体在类似的700个聚合物结构，迄今已被测量，以预测超过11,000个均聚物的气体分离行为，这些性能以前没有测试。为了测试该算法的准确性，我们合成了两种最有前途的聚合物膜预测这种方法，并发现它们超过了CO2/CH 4分离性能的上限。这种ML技术是使用相对较小的实验数据（并且没有模拟数据）进行训练的，显然代表了探索可用于聚合物膜设计的巨大相空间的创新手段。
The field of polymer membrane design is primarily based on empirical observation, which limits discovery of new materials optimized for separating a given gas pair. Instead of relying on exhaustive experimental investigations, we trained a machine learning (ML) algorithm, using a topological, path-based hash of the polymer repeating unit. We used a limited set of experimental gas permeability data for six different gases in similar to 700 polymeric constructs that have been measured to date to predict the gas-separation behavior of over 11,000 homopolymers not previously tested for these properties. To test the algorithm's accuracy, we synthesized two of the most promising polymer membranes predicted by this approach and found that they exceeded the upper bound for CO2/CH4 separation performance. This ML technique, which is trained using a relatively small body of experimental data (and no simulation data), evidently represents an innovative means of exploring the vast phase space available for polymer membrane design.